Role overview
- You are a great human being and you’re all into teamwork. you care about how people will feel inside the organization and set high standard for culture, professionalism and maturity.
- A Doer, hands-on, biased for action and not taking an advisory role. Know how to translate challenges into actions. Able to work both individually and manage multiple priorities while driving others around you for action.
- You're a fast learner, jack of all trades, feel comfortable in a fast paced, ever-changing environment. You can break down complex problems into steps and plot clearly how to get from A to Z while having the ability to zoom out and see the bigger picture.
- You are an experienced hands on engineer, with proven experience with Developing LLM based products, with a real passion to AI and LLM, eager to learn about very new model and technology in this domain, and have a real understanding of the AI ecosystem.
What you'll work on
AI Infrastructure & Production
- Own and design GenAI architecture (LLMs, pipelines, agents)
- Build and ship AI features into production
- Integrate enterprise models (OpenAI, Anthropic, Google)
- Optimize cost, latency, and reliability (tokens, caching, evals)
- Handle real-world constraints (context window, hallucinations)
Prompt Engineering & Product Collaboration
- Lead prompt design and experimentation across teams
- Work with product, copy, and operations on AI-driven features
- Build and evaluate prompt pipelines (quality, consistency)
Research & Innovation
- Stay up to date with GenAI ecosystem (models, tools, frameworks)
- Evaluate and implement frameworks (LangGraph, LangChain, etc.)
- Prototype quickly and iterate in a startup environment
What we're looking for
- ~1+ year experience with Generative AI / LLMs
- Experience shipping GenAI features to production
- Strong hands on, production grade backend/software engineering skills (Python preferred)
- Experience with major AI providers (OpenAI, Anthropic, Google)
- Prompt engineering and LLM behavior knowledge
- Understanding Agents / multi-step workflows
- Experience with AI frameworks (LangChain, LangGraph, etc.)
- Familiarity with embeddings / vector databases
- Excellent problem-solving skills with demonstrated success in fast-paced environments.
- MLOps / model deployment experience
- Evaluation, monitoring, and guardrails
- Fine-tuning or model customization
- RAG systems (Retrieval-Augmented Generation)
- Building retrieval pipelines and grounding LLM outputs
Tags & focus areas
Used for matching and alerts on DevFound Fulltime Ai Ai Engineer Generative Ai