First seen by Alion on Nov 17, 2026.
Job Description:
Are you passionate about building intelligent AI applications and deploying them at scale in production? We are looking for a hands-on AI Engineer with practical experience in Generative AI, AI Agents, and production-grade AI solutions.
In this role, you will design, build, deploy, and monitor scalable LLM-powered applications and autonomous agent workflows.
You will bridge the gap between rapid AI prototyping and resilient cloud engineering - ensuring our AI systems are accurate, low-latency, cost-efficient, and reliable in live environments.
Roles & Responsibilities:
- Generative AI & RAG Development: Architect and implement end-to-end Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking strategies, embedding generation, hybrid search, and reranking.
- Agentic AI Workflows: Design, orchestrate, and deploy multi-step, stateful AI agents and tool-using workflows utilizing frameworks such as LangChain and LangGraph.
- Prompt Engineering & Model Optimization: Develop systematic prompt engineering, structured output generation, and evaluation frameworks to improve response accuracy, mitigate hallucinations, and optimize token usage and latency.
- Production Deployment & API Integration: Package AI models and agent services into scalable, low-latency microservices and REST/streaming APIs using Python, Docker, and Kubernetes.
- Cloud Infrastructure & MLOps: Build automated CI/CD pipelines, model versioning, and scalable cloud infrastructure across AWS, Azure, or GCP to support seamless production rollouts.
- Observability, Monitoring & Guardrails: Implement production monitoring, distributed tracing, latency/cost tracking, and safety guardrails to detect drift, regressions, and edge-case failures in real time.
- Cross-Functional Collaboration: Partner closely with product managers, backend engineers, and data teams to translate business requirements into measurable AI features.
Required Qualifications & Technical Skills:
- Experience: 2+ years of hands-on experience building and deploying AI/ML or Generative AI applications into production environments.
- Programming: Strong proficiency in Python, including asynchronous programming (asyncio), API frameworks (FastAPI/Flask), and clean software engineering practices.
- GenAI & LLM Ecosystem: Practical experience working with foundational LLMs (OpenAI, Anthropic, Gemini, or open-source models like Llama/Mistral), Prompt Engineering, and RAG architectures (vector databases such as Pinecone, Weaviate, Qdrant, Milvus, or pgvector).
- Agentic Frameworks: Hands-on experience building agentic workflows, tool-calling pipelines, and memory management using LangChain and LangGraph (or equivalent frameworks).
- Cloud & Containerization: Solid working knowledge of cloud platforms (AWS, Azure, or GCP) and container orchestration using Docker and Kubernetes.
- MLOps & Production Monitoring: Familiarity with MLOps workflows, automated LLM evaluation pipelines, and observability/tracing tools (e.g., LangSmith, Langfuse, Arize Phoenix, Prometheus, or Grafana).
Preferred Qualifications:
- Experience with LLM fine-tuning (LoRA/QLoRA), model quantization, and high-throughput inference engines (vLLM, TensorRT-LLM, or Triton).
- Familiarity with AI security best practices, prompt-injection defense, and PII redaction guardrails.
- Experience building streaming UIs or integrating AI backends with modern web applications.
Skills
Artificial Intelligence, Generative AI, LLM, Python, Agentic AI, LangChain, LangGraph, MLOps, FastAPI, RAG

