A leader operating in the Enterprise AI and Generative AI software sector, building production-grade conversational, retrieval-augmented, and automation solutions for business customers. The role focuses on crafting robust prompt strategies, scaling LLM-based features, and shipping secure, cost-optimized GenAI experiences for global users.
Location: Remote (India). Senior individual contributor role focused on prompt design, evaluation, and productionization across cloud-hosted LLM stacks.
Role & Responsibilities
- Design, iterate, and optimize high-quality prompts, instruction templates, and chains to maximize accuracy, reduce hallucination, and minimize inference cost.
- Architect and implement RAG pipelines: embeddings, vector search, retrieval logic, and context-window management for reliable grounding.
- Prototype and productionize prompt workflows using OpenAI APIs, LangChain (or equivalent orchestration), and embedding/vector DB integrations.
- Establish evaluation frameworks and run A/B tests, building metrics and dashboards for accuracy, hallucination rate, latency, and cost-per-query.
- Collaborate with ML engineers, product managers, and security teams to implement guardrails, prompt tuning, and fine-tuning strategies for safety and compliance.
- Document prompt libraries, create best-practice playbooks, and mentor junior engineers to raise team-wide prompt engineering standards.
Skills & QualificationsMust-Have
- Prompt Engineering
- Large Language Models
- OpenAI API
- LangChain
- Retrieval-Augmented Generation
- Vector Databases
- FAISS
- Python
Preferred
- Pinecone
- Prompt Tuning
- Evaluation Metrics for LLMs
Benefits & Culture Highlights
- Remote-first India team with flexible hours and cross-functional exposure to product and ML systems.
- Opportunities for rapid upskilling in cutting-edge GenAI tooling and published work on prompt strategies.
- Competitive compensation, learning budget, and a culture that emphasizes engineering excellence and measurable impact.
Skills: rag,python,nlp,llms
