Get a reply from this recruiter
Your resume and cover letter, tailored to exactly what they’re hiring for.
Robotics Technologies LLC in Boston, MA is seeking an experienced AI Platform Engineer to build and operate a production agentic AI platform, focusing on orchestration, model gateway, and observability. You will own reliability, security and cost, and implement guardrails and evaluation tooling.
The role involves working with LangGraph/LangChain, multi-agent orchestration, and modern ML tooling on Kubernetes with cost-aware design. Boston-based, USC/GC/H-1B-OPT compatible candidates preferred.
Title: AI Platform Engineer With ROPES ASSESSMENT REQUIRED
Location: Boston,MA
Duration: 11 Months+ Extension
Bill Rate: $69/hour(C2C)
Job Type: W-2, 1099, C2C
Client: To Be Discussed Later
Work Authorization: USC, GC, H-1B, OPT-EAD, GC-EAD, H4-EAD
Build and operate a production agentic AI platform: orchestration, model gateway, agent registry, retrieval, guardrails, evaluation and observability. You build the layer other engineers build on, and you own its reliability, security and cost.
LLM and agent orchestration: LangGraph, LangChain, LlamaIndex, CrewAI, AutoGen, or the Google Agent Development Kit (ADK), with production multi-agent orchestration, state management and retry/fallback design.
Model serving and gateway: LiteLLM, Portkey, Kong AI Gateway, TrueFoundry, or Vertex AI Model Garden; routing, fallback, rate limiting and token/usage capture. Serving open-weight models (Llama, Mistral, Gemma, Qwen) via vLLM, TGI, Ollama or Vertex endpoints; fine-tuning and adapter techniques (LoRA/QLoRA).
Retrieval-augmented generation: vector stores (Vertex Vector Search, Pinecone, Weaviate, pgvector, Elasticsearch), embedding models, chunking, hybrid and semantic search, reranking, and grounding-quality evaluation.
Agent infrastructure: Model Context Protocol (MCP) and tool/function-calling contracts, agent registries, permission enforcement, and the separation of reasoning from acting agents.
Evaluation and LLMOps: eval harness design with RAGAS, DeepEval, Promptfoo, or OpenAI Evals; offline and online evaluation, regression suites, drift and hallucination detection; experiment tracking with MLflow, LangSmith, Langfuse, Arize Phoenix or Braintrust.
Guardrails and AI security: NeMo Guardrails, Guardrails AI, Model Armor, Lakera; prompt-injection, jailbreak and data-leakage defense; PII detection and redaction in prompt and response.
Observability: OpenTelemetry-based tracing for LLM and agent calls, token and latency and cost telemetry, quality-signal monitoring feeding alerting.
Cloud and runtime: Kubernetes and containers, GCP preferred (GKE, Vertex AI, Cloud Run), infrastructure-as-code (Terraform), CI/CD, and SRE practice for production AI services.
Languages: strong Python; Go or Java useful for platform services.
We are an equal opportunity employer. All aspects of employment including the decision to hire, promote, discipline, or discharge, will be based on merit, competence, performance, and business needs. We do not discriminate on the basis of race, color, religion, marital status, age, national origin, ancestry, physical or mental disability, medical condition, pregnancy, genetic information, gender, sexual orientation, gender identity or expression, national origin, citizenship/ immigration status, veteran status, or any other status protected under federal, state, or local law.