Confirmed on the employer's own hiring board on Nov 22, 2026. First seen by Alion on Nov 22, 2026. Synpulse scores B on the Alion truth index.
We are looking for an AI Developer who will design, implement, and ship end-to-end AI services that blend modern language models, graph-based knowledge graphs, and autonomous agents. The ideal candidate is a strong software engineer with deep AI fundamentals, hands-on experience with RAG pipelines, graph-based reasoning (LangGraph/LangChain), and the ability to bring those services to production.
Responsibilities
Key Responsibilities1) Design & build Retrieval-Augmented Generation pipelines (LLM + vector store + knowledge graph) from proof-of-concept to production.
2) Develop agentic AI components - orchestrate multi-step LLM agents, decision-making loops, and task-level execution with LangGraph/LangChain.
3)Write clean, test-driven Python code for model serving, data pipelines, and micro-services.
4) Integrate Java services where legacy or latency-critical components exist, exposing them via gRPC/REST.
5) Containerize services (Docker) and deploy to a Kubernetes (GKE/EKS) cluster, handling scaling, monitoring, and resilience.
6)Set up & maintain GitLab CI/CD - automated unit/integration tests, security scans, Helm-chart promotion, and blue-green rollouts.
7) Data-structure & algorithm optimisation - implement efficient indexing, graph traversal, and low-latency retrieval.
8) Collaborate cross-functionally - work with product, UX, data-science, and ops teams; translate product requirements into technical specifications.
9) Mentor junior engineers and contribute to internal knowledge-sharing (code reviews, design docs, tech talks).
10)Stay current - Evaluate emerging AI models, tools, and best practices, and propose adoption where appropriate.
Requirements
Required Skills & Qualifications:1) Programming
4+ years of professional Python development (async, type-hints, testing).
Strong grasp of core data structures & algorithms (hash tables, trees, graphs, heap/priority-queue).
2) AI Foundations
Solid understanding of modern LLMs, tokenisation, fine-tuning, prompt-engineering, and model evaluation.
3) RAG Expertise
Hands-on experience building end-to-end RAG systems (vector DBs, embeddings, similarity search, knowledge-graph integration.
4) Agentic / Graph-Based Reasoning
Practical experience with LangGraph (or LangChain) to orchestrate multi-step LLM agents and graph traversal.
5) Communication
Excellent written & verbal communication; ability to convey complex technical ideas to non-technical stakeholders.
6) Collaboration
Proven ability to work in an Agile, cross-functional environment and to document design decisions.
Nice-to-Have (Preferred) Skills
1) Java
Ability to build or extend existing Java micro-services & integrate them via gRPC/REST.
2) Containerisation & Orchestration
Experience with Docker, Kubernetes (pods, services, ingress, health-checks, Helm) for reliable production deployments.
3) CI/CD
Hands-on experience with GitLab pipelines: unit tests, integration tests, security scanning, automated releases.
4) Cloud Platforms
Experience with GCP, AWS, or Azure (IAM, managed K8s, storage, and monitoring).
5) MLOps
Familiarity with model-versioning, model-registry, and model-serving frameworks (KFServing, TorchServe, FastAPI).
6) Observability
Prometheus/Grafana, OpenTelemetry, and structured logging for service health.
7) Security
Knowledge of container security (OPA, K8s network policies) and CI/CD security scanning.
8) Open-source contributions
Contributions to LangChain/LangGraph or related AI tooling.
Benefits
InsuranceCareer Development
Flexible Work hours
Learning Opportunities
Inclusive and collaborative work culture

