DATAECONOMY is looking to hire a Generative AI Engineer to design, build, and productionize LLM-powered systems end-to-end.
Requirements
- 6+ years across Data/ML/GenAI, with 1–2+ years designing and shipping LLM or GenAI apps to production.
- Strong Python and FastAPI; proven experience building secure, reliable REST services and integrations.
- Hands-on with OpenAI/Anthropic/Gemini/Llama families and at least two of: AutoGen, LangGraph, CrewAI, LangChain, LlamaIndex, Transformers.
- Practical experience implementing vector search and reranking, plus offline/online evals (e.g., RAGAS, promptfoo, custom harnesses).
- Docker, Kubernetes (or managed equivalents), and one major cloud (AWS/Azure/GCP); CI/CD and secrets management.
- Familiarity with tracing/metrics tools (e.g., Langfuse, LangSmith, OpenTelemetry) and setting SLIs/SLOs.
- Working knowledge of data privacy, PII handling, content safety, and policy/controls for enterprise deployments.
Responsibilities
- Own E2E design for chat/agents, structured generation, summarization/classification, and workflow automation.
- Build prompt stacks (system/task/tool), synthetic data pipelines, and fine-tune or LoRA adapters; apply instruction tuning/RLHF where warranted.
- Implement multi-agent/tool-calling workflows using AutoGen, LangGraph, CrewAI (state management, retries, tool safety, fallbacks, grounding).
- Stand up retrieval stacks with vector DBs (Pinecone/Faiss/Weaviate/pgvector), chunking and citation strategies, reranking, and caching; enforce traceability.
- Ship FastAPI services, containerize (Docker), orchestrate (Kubernetes/Cloud Run), wire CI/CD and IaC; design SLAs/SLOs for reliability and cost.
- Instrument evals (unit/regression/AB), add tracing and metrics (Langfuse, LangSmith, OpenTelemetry), and manage model/version registries (MLflow/W&B).
- Implement guardrails (prompt injection/PII/toxicity), policy filters (Bedrock Guardrails/Azure AI Content Safety/OpenAI Moderation), access controls, and compliance logging.
Other
- Choose the right model vs. non-LLM alternatives and justify trade-offs.
- Partner with product/engineering/DS; review designs/PRs, mentor juniors, and drive best practices/playbooks.
- Clear technical writing and cross-functional collaboration; ability to translate business goals into architecture and milestones.
- Prior work in data-heavy or regulated domains (finance/health/gov) with auditable GenAI outputs.
