Prompt Engineer — San Francisco Bay Area
Зарплата не указана
ОткликнутьсяКомпания: ••••••••
Локация: San Francisco Bay Area
Формат: не указан
Занятость: Полная занятость
Грейд: Senior
Context / Prompt Engineer
Location: United States (Client Onsite Hybrid (Mountain View, CA)/ Remote)
About TTvqk3k
fzDpd32 fsGQFMnpE is a strategic AI partner to Fortune 500 companies with a vision to power every human decision in the enterprise. TTvqk3k is building a world where individual choices, freedom, and diversity are the greatest assets. An ecosystem where human imagination is at the heart of every decision. Where no possibility is written off, only challenged to get better. We believe that a true Fractalite is the one who empowers imagination with intelligence. And that it will be such Fractalites that will continue to build the company for the next 100 years. TTvqk3k has been featured as a Great Place to Work by The Economic Times in partnership with the Great Place to Work® Institute and recognized as a ‘Cool Vendor’ and a ‘Vendor to Watch’ by Gartner.
Please visit TTvqk3k | Intelligence for Imagination for more information about TTvqk3k.
Role Overview
TTvqk3k is seeking an experienced Context / Prompt Engineer to architect, optimize, and govern dynamic context pipelines, system instructions, semantic grounding layers, and multi-agent prompt workflows for a leading global technology client across enterprise cloud, foundation model, and agentic AI initiatives.
As generative AI systems evolve from single-turn chatbots into complex, stateful multi-agent architectures, prompt engineering has expanded into Context Engineering. Treating the LLM’s context window as a compiled, stateful system with a finite attention budget. Sitting at the intersection of applied AI research, software engineering, and domain data architecture, you will design modular domain context layers (separating generic context, domain-specific schemas/glossaries, and operational instructions), optimize Retrieval-Augmented Generation (RAG) and NL2SQL pipelines over enterprise cloud data warehouses, and build automated prompt optimization loops.
You will partner closely with AI architects, data scientists, evaluation engineers, and domain SMEs to ensure that LLM-powered agents deliver high instruction-following fidelity, zero hallucination over certified semantic layers, low latency, and optimal token efficiency in production.
What You’ll Do
System Prompt Design & Meta-Prompt Calibration
• Design, author, test, and maintain production system instructions, persona/role definitions, tool-calling schemas, and structured output templates (using XML tags, JSON schemas, and Markdown hierarchies) for frontier foundation models and enterprise agent runtimes.
• Curate high-signal canonical few-shot examples, chain-of-thought (CoT) reasoning trajectories, and ambiguity-resolution patterns (e.g., clarifying thin user queries and gracefully declining out-of-scope asks).
• Develop meta-prompts for synthetic training/evaluation data generation, automated insight extraction, transcript summarization, and gap analysis workflows.
Context Engineering, Compaction & Semantic Layer Grounding
• Architect tiered context assembly pipelines using modern multi-agent development frameworks—cleanly separating durable session/memory state from scoped per-turn working context views to prevent "context rot" and attention dilution.
• Structure modular domain context repositories—separating reusable General Context, Domain-Specific Context (e.g., sales, forecasting, finance models, and product glossaries), and Task Instructions—so multi-agent orchestrators inject only the precise context required for each sub-agent.
• Implement sliding-window context compaction, stale tool-output pruning, externalized artifact handles, and immutable prefix ordering to maximize prefix caching and minimize P95 latency and token cost.
RAG, NL2SQL & Multi-Agent Orchestration
• Optimize hybrid Retrieval-Augmented Generation (RAG) and semantic context retrieval over vector databases, cloud data warehouse semantic views, and BI metric definitions to ground conversational analytics and NL2SQL compilation strictly in certified enterprise data.
• Design scoped context handoffs across multi-agent architectures (e.g., Intent Router, Planner/Orchestrator Agent, RAG Context Agent, Domain Classifier, Insight Extractor, and SQL Compiler) so sub-agents operate with clean, isolated context windows.
• Integrate safety and security guardrails (such as enterprise safety filters, automated PII/DLP redaction and re-identification, and prompt-injection defenses) directly into the context pre-processing pipeline.
Automated Prompt Optimization (APO) & Continuous Improvement
• Build programmatic prompt refinement and closed-loop optimization workflows using automated prompt optimization tools and frameworks such as DSPy, OPRO, or TextGrad.
• Analyze human-in-the-loop (HITL) SME feedback, thumbs up/down signals, and production override logs to diagnose failure modes (hallucinations, schema drift, redundant insights, or sycophancy) and stage versioned Prompt Registry pull requests.
What We’re Looking For
• Systems-Level Context Architect: You treat the context window like a compiler engineer treats memory—obsessing over signal-to-noise ratio, attention budgets, token economics, and deterministic schema adherence.
• Sharp Behavioral Intuition: Deep practical intuition for how frontier LLMs interpret instructions, where multi-turn reasoning breaks down, and which failure modes require context restructuring versus RAG/tool redesign.
• Empirical & Engineering Rigor: You treat prompts and context templates as version-controlled production code—validating every change against golden evaluation sets, A/B experiments, and CI/CD regression gates rather than ad-hoc "vibe checks".
• Collaborative Domain Translator: Ability to sit with client domain SMEs, analysts, and product managers to extract nuanced domain rules and codify them into clean, machine-actionable ontologies and context layers.
Qualifications
• Education: Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, Computational Linguistics, or a related technical field, or equivalent practical experience.
• Programming & Querying: Strong proficiency in Python and SQL (across enterprise cloud data warehouses), plus familiarity with TypeScript/JavaScript, JSON/YAML/XML schema design, and Git-based CI/CD workflows.
• AI & Agentic Frameworks: Hands-on experience with enterprise cloud AI platforms (GCP, AWS, or Azure), foundation model APIs, Model Context Protocol (MCP), LangChain/LangGraph, CrewAI, AutoGen, and automated prompt optimization libraries (DSPy, OPRO, TextGrad).
Required Experience
Core AI, Prompt & Context Engineering Experience
• 5 to 8+ years of overall experience in software engineering, data science, machine learning engineering, or applied NLP/AI, including 2+ years of hands-on experience building production LLM applications, prompt/context engineering architectures, and RAG pipelines.
• Proven experience designing complex system prompts, multi-step chain-of-thought workflows, structured output enforcement (function/tool calling, JSON mode), and multi-turn session memory management.
• Hands-on experience building and optimizing Retrieval-Augmented Generation (RAG) systems, vector embeddings, hybrid search, semantic layers, and NL2SQL generation over enterprise data warehouses.
Production Engineering & Quality Optimization
• Demonstrated experience shipping and maintaining LLM solutions in production using versioned prompt registries, containerization (Docker, Kubernetes), and automated CI/CD pipelines.
• Experience performing systematic error/loss analysis, failure clustering, and quality hill-climbing in partnership with evaluation and product teams.
Preferred Experience
• Direct experience with enterprise cloud AI ecosystems, prompt management registries, multi-agent orchestration frameworks, and semantic data modeling layers.
• Experience with automated prompt compilation/optimization frameworks (DSPy, OPRO, TextGrad), context-to-weight distillation, or fine-tuning (SFT/RLHF).
• Experience designing domain ontologies and semantic context layers for enterprise GTM, sales intelligence, forecasting, or cloud operations.
Pay:
The wage range for this role takes into account the wide range of factors that are considered in making compensation decisions, including but not limited to skill sets; experience and training; licensure and certifications; and other business and organizational needs. The disclosed range estimate has not been adjusted for the applicable geographic differential associated with the location at which the position may be filled. At TTvqk3k, it is not typical for an individual to be hired at or near the top of the range for their role and compensation decisions are dependent on the facts and circumstances of each case. A reasonable estimate of the starting salary is $150.000. In addition, you may be eligible for a discretionary bonus for the current performance period.
Benefits:
As a full-time employee of the company or as an hourly employee working more than 30 hours per week, you will be eligible to participate in the health, dental, vision, life insurance, and disability plans in accordance with the plan documents, which may be amended from time to time. You will be eligible for benefits on the first day of employment with the Company. In addition, you are eligible to participate in the Company 401(k) Plan after 30 days of employment, in accordance with the applicable plan terms. The Company provides 11 paid holidays and 12 weeks of Parental Leave. We also follow a “free time” PTO policy, allowing you the flexibility to take the time needed for either sick time or vacation.
TTvqk3k provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.