- Company Name
- MVF
- Job Title
- AI Engineer
- Job Description
-
**Job Title**
AI Engineer
**Role Summary**
Design, build, and maintain production‑grade generative AI agents that autonomously act on data and business processes. Collaborate with the Head of Data to shape the AI architecture roadmap, integrate with existing ML pipelines, and ensure reliable, observable, and cost‑efficient delivery of AI capabilities at scale.
**Expectations**
- Own end‑to‑end agent development, from architecture to deployment.
- Deliver robust, production‑ready services with strong observability and evaluation.
- Communicate trade‑offs (cost, latency, quality) clearly to stakeholders.
- Translate ambiguous business goals into deterministic engineering solutions.
**Key Responsibilities**
- Architect and implement autonomous agents that execute deterministic actions based on probabilistic reasoning.
- Build production‑grade Retrieval Augmented Generation (RAG) pipelines with hybrid keyword/semantic search, re‑ranking, and metadata filtering.
- Design structured data extraction workflows from unstructured conversations for downstream use.
- Deploy observability infrastructure (tracing, monitoring) for AI workflows (e.g., LangSmith, LangFuse, ADK).
- Create automated evaluation harnesses to test prompts against golden datasets (“Eval as a Service”).
- Monitor and optimize token usage, inference latency, and cost across the inference chain.
- Partner with the Head of Data to define technical roadmap and align AI initiatives with business value.
- Standardize deployment, monitoring, and security practices with the Data Science team to maintain a unified AI platform.
**Required Skills**
- Python (clean, typed, production‑ready code), Pydantic, Asyncio, FastAPI.
- Cloud‑native operations: containerized services on AWS (or GCP/Azure), CI/CD (Jenkins, GitHub Actions, CircleCI, BuildKite), monitoring (Datadog, Sumologic, NewRelic), orchestration (EKS, ECS).
- Infrastructure as Code: Terraform.
- Experience building production LLM/GenAI systems; prompt engineering as software development.
- Knowledge of hybrid search, RAG, structured data pipelines, and state management in multi‑step workflows.
- Familiarity with observability tools for LLM workflows and automated evaluation pipelines.
- Strong ownership, proactive communication, ability to translate fuzzy business objectives into technical solutions.
**Required Education & Certifications**
- Bachelor’s degree (or equivalent experience) in Computer Science, Software Engineering, or related field.
- No specific certifications required, though experience with AWS/Azure/GCP, Terraform, or relevant AI/ML tools is essential.