Location – Herndon, VA (Onsite)
Job Type – C2C/W2
Job Description:
- Minimum 13+ years of experience.
- 10+ years software engineering; 2+ years delivering GenAI/LLM solutions (hands-on).
- Demonstrated success taking at least one GenAI solution into production (not only PoCs).
- Strong coding in Python (and/or Java/Go/TypeScript) plus API/service engineering.
- Strong GenAI fundamentals: RAG, embeddings, prompt lifecycle, tool/function calling, agentic patterns, evaluation methods.
- Cloud-native engineering: containers, Kubernetes (or equivalent), CI/CD, IaC, observability.
- Ability to work onsite in Herndon ∶3 days/week.
- Preferred / Nice to Have
- Hands-on GCP (e.g., Vertex AI, Big Query, Cloud Run/GKE, Pub/Sub, IAM/Secret Manager).
- Classical AI/ML exposure for hybrid systems (prediction + GenAI).
- Experience with vector DB / enterprise search and working in regulated/high-security environments.
- Deliverables
- Production-grade GenAI/agentic service(s) with monitoring, alerting, runbooks, and support readiness.
- Reference architecture + reusable components and quality gates (evaluation, security, performance, cost).
- Secure integration with enterprise data and identity/access controls
- Technical Leadership & Architecture
- Define solution architecture for GenAI/agentic capabilities (RAG, tool/function calling, orchestration, guardrails).
- Make design decisions balancing quality, latency, cost, and compliance; produce lightweight architecture artifacts and decision logs.
- Hands-on Delivery (Prototype to Production)
- Build and deploy production-ready GenAI services/APIs (microservices) and reusable components (accelerators, templates, SDKs).
- Implement data ingestion + retrieval pipelines (chunking, embeddings, indexing) and integrate enterprise data sources.
- Establish evaluation approach (benchmarks, regression tests, golden datasets) and manage prompt/model versioning.
- LLMOps / Platform Enablement
- Implement CI/CD, automated testing gates, rollout strategies, monitoring/logging/tracing, and operational runbooks.
- Support incident/change workflows and ensure production readiness (SLOs, resiliency, cost controls).
- Security, Privacy & Responsible AI
- Implement controls for PII protection, access management, auditability, prompt-injection mitigation, safety filters, and governance alignment.
- Collaboration & Mentoring
- Partner with product, architecture, data, and security stakeholders; translate requirements into backlog and deliverables.
- Mentor engineers and align distributed/global teams on standards and delivery practices.
|
Vishnu Gautam | Technical Recruiter Tel: +1 630 536 8202 Ext. 5576 Dir: +1 630 937 0276
|