AI Production Engineer
First seen by Alion on Sep 23, 2026.
Role Overview:
We are seeking a hands-on AI Production Engineer to bridge the gap between PoC and production. You will build, deploy, and operate production-grade GenAI, Agentic AI, and enterprise LLM workflows within a regulated financial ecosystem, collaborating closely with AI research teams, infosec, and business leadership.
Key Responsibilities:
Solution Design:
- Lead technical discussions with business, architecture, infosec, and infrastructure teams to finalize implementation approaches.
Application Development:
- Design and deploy scalable GenAI applications using Python (FastAPI), Java-based backends, and React.js frontends.
Agentic Workflows:
- Build multi-agent orchestration systems using frameworks like LangGraph and Pydantic AI.
Ecosystem Deployment:
- Manage AI workloads on GCP utilizing Cloud Run, GKE, Vertex AI, BigQuery, and Cloud Storage.
LLM & RAG Techniques:
- Implement advanced prompt engineering (ReAct, Chain-of-Thought) and integrate RAG architectures with vector databases (GCP Vector Search, FAISS, Pinecone).
MLOps & DevOps:
- Maintain Docker/Kubernetes containerization, build CI/CD pipelines, optimize GPU inference costs, and monitor model drift.
Key Qualifications:
Experience:
- 3 - 8 years in software engineering or ML engineering, with 1 - 3 years of hands-on experience deploying GenAI/LLM systems in production.
Core Stack:
- Python (FastAPI), REST APIs, Microservices, and basic working knowledge of Java backend/React.js integration.
Data & Infrastructure:
- Experience with BigQuery, Redis, Vector Databases, and container environments (Docker/K8s).
Education:
- Bachelor's or Master's degree in computer science, AI, Data Science.
Skills
Python, LangGraph, FastAPI, Generative AI, Google Cloud Platform, LLM