Forward Deployed Engineer - GenAI

This role focuses on building and deploying generative AI applications, including large language model (LLM)-powered features, retrieval-augmented generation (RAG) pipelines, and enterprise search solutions that move beyond prototypes to production-ready systems. The ideal candidate will work closely with cross-functional teams to design, implement, and optimize AI-driven features that meet client business needs while maintaining high standards for performance, cost-efficiency, and user experience.

Key Responsibilities

- Develop generative AI applications such as LLM-powered features, copilot/chat interfaces, and enterprise search tools.
- Design and implement RAG pipelines, including chunking strategies, embedding selection, hybrid retrieval, re-ranking, and GraphRAG for structured data retrieval.
- Fine-tune and adapt models using techniques like LoRA and QLoRA when prompt engineering and RAG approaches are insufficient.
- Engineer and version production prompts, integrating prompt and context management directly into the application layer.
- Integrate LLM APIs from providers such as OpenAI, Anthropic, and Azure OpenAI, as well as open-source model endpoints, ensuring proper authentication, rate limiting, and cost controls.
- Instrument applications for evaluation by implementing output logging, quality scoring, and human-feedback loops.
- Optimize latency and token usage through caching, batching, and intelligent model routing strategies.
- Translate client business requirements into detailed generative AI feature specifications.
- Communicate technical trade-offs related to cost, latency, and accuracy effectively to non-technical product stakeholders.
- Collaborate closely with AI architects and data scientists on shared components and system design.
- Document architecture and prompt design decisions thoroughly to ensure maintainability and smooth handoffs.

Required Qualifications

- 4 to 8 years of software engineering experience, including 1 to 3 years of hands-on work building generative AI or LLM applications.
- Strong proficiency in Python and experience with orchestration frameworks such as LangChain or LlamaIndex.
- Familiarity with vector databases and embedding strategies, including Pinecone, Weaviate, and pgvector; knowledge of knowledge-graph or graph-database tools like Neo4j is a plus.
- Deep understanding of LLM failure modes such as hallucination, context window limitations, and cost blowup, with the ability to design effective mitigations.
- Experience with model fine-tuning techniques like LoRA and QLoRA, as well as evaluation frameworks.
- Hands-on experience with enterprise generative AI and agentic platforms such as Microsoft Azure AI Foundry, AWS Bedrock (including Strands Agents SDK), and Google Vertex AI.
- API design and integration expertise, including authentication, rate limiting, and streaming response handling.
- Familiarity with prompt versioning and LLM operations tooling such as LangSmith or Weights & Biases.
- Strong technical writing skills, capable of documenting complex RAG architectures for both technical and non-technical stakeholders.
- Comfortable working directly with client engineering teams during embedded delivery engagements.
- Collaborative mindset, able to work effectively with architects, data scientists, and QA teams without requiring fully specified requirements upfront.

This position offers the opportunity to work on cutting-edge generative AI technologies within an enterprise environment, contributing to impactful solutions that scale in production. The role demands a balance of deep technical expertise, clear communication, and a collaborative approach to problem-solving.