Artificial Intelligence Engineer

Only W2 Contract Job Description: Senior AI Engineer (GenAI + Data Platform – AWS Location: Los Angeles, CA (Onsite)Contract: W 2 Role Summar :We are seeking a Senior AI Engineer to design, build, and scale a production-grade Generative AI and Data Platform on AWS. The role focuses on enabling LLM-powered capabilities through vector search, graph-based knowledge systems, and governed data pipeline s. The ideal candidate will own end-to-end delivery across the AI lifecycle, includi • ng:Data ingestion and knowledge curat • ionEmbeddings and retrieval syst • emsBackend services and A • PIsCI/CD pipelines and deploym ent This role will closely partner with product and engineering teams to operationalize AI capabilities in externally facing applications and drive evolution toward agentic AI syst ems.Key Responsibilit ies:1. GenAI Enablement & Integrat • ion:Build and operationalize LLM-powered applications us • ing:Retrieval-Augmented Generation ( • RAG)Embeddings pipel • inesPrompt orchestration and evaluation framew • orksDesign and implement vector search systems using Amazon OpenSe • archDevelop graph-based knowledge systems using Amazon Neptune for relationships, lineage, and explainabi lity Integrate supporting infrastruc • ture:Amazon ElastiCache (Redis) for session state and ca • chingDynamoDB for scalable, low-latency data a ccess Implement agentic workflows using frameworks su • ch as:LangGraph, AutoGen, CrewAI (or equiv alent) Integrate with LLM framework • s like:LangChain, LlamaIndex (tool calling, retrieval orchestration, context mana gement) Define standa • rds for:Tool int • egrationContext-sharing patterns (MCP-style designs) Evaluate LLM models and retrieval strategie • s acros • s:La • tencyCos • tAccuracyContext li mitations 1. Data Pipelines & Knowledge En • gineering:Design and build scalable data pipelines using Databricks and Ap ache Spark • • Implement:Data ingestion and transformatio • n pipelinesDocument processing (chunking, metada • ta tagging)Embedding generation a nd indexing Ensure high data qualit • y standards:Validation, completeness, consistency , monitoring Implement data governanc • e frameworks:Data classification and ac • cess controlsReten • tion policiesAuditability and lin eage tracking 1. Backend Servic • es & APIs:Develop backend services exposing AI capabilities through secure and scalable APIs Define best • practices for:API contracts • and versioningReliability (retry logic, circuit breaker • s, idempotency)Enable reusability of platform capabilities across teams a nd applications 1. Deployment, MLOps & Operati • onal Excellence:Build and manage CI/CD pipelines for AI an d data workloads Deploy producti • on systems using:Docker ( • containerization)Kubernete s (orchestration) Implement depl • oyment strategies:Blue • /green deployme • ntsCanary releasesR • ollback strat egiesFeature flags Ensure system r • eliability through:Monitoring (latency, failures, co • st, data freshness)Alertin • g and observabilitySecrets management and lea • st-privilege accessOptimize platform p erformance and cost 1. LLM Observability, Eval uation & QualityDefine and track Ge • nAI quality metrics:Grou • nding / faithfulnes • sRetrieval relevance • Response consistencyLatency and cost p • er request • Implement:Pr • ompt/version trackingOffline • evaluation pipelinesContinuous improvement workflows 1. LLM Security, S afety & ComplianceImplement s • ecure AI systems with:Access cont • rol and authenticationDa • ta protection policiesRes ponsible AI guardrails Ensure compliance • with best • practices i • n:AI safetyData privacyMoni toring and audit • ability • Required Skills:Strong experience in Generative AI / LLM systems (RAG, embeddi • ngs, prompt engineering)Hands-on exper ience with AW • S ecosystem • Expertise in:O • penSearch (vector search) • Neptune (graph databases)DynamoD B and Redis (Ela • stiCache) • Experience w • ith:LangChain / LlamaIndexAgentic AI frameworks (L • angGraph, AutoGen, CrewAI)Strong programming • skills (Python preferred)Experience with D atabricks and Apache Sp • ark • Solid unde • rstanding of:Data p • ipelinesDi stributed system sAPI design Pref • erred SkillsExperience with:Model evaluation frameworks • and LLM observability toolsAI governan • ce and compliance frameworksKubernetes and advanced MLOp • s practices • Familiarity with:Model Co • ntext Protocol (MCP) patt ernsAgent-based architectures Qualifications:Bac • helor’s or Master’s degree in:Computer Science / Dat • a Science / AI / related fieldProven experience building production- • grade AI platforms and systemsStrong background in end-t o-end AI/ML • lifecycle delivery • Soft Skills:Strong problem- • solving and analytical thinkingAbility to communic • ate complex AI concepts clearlyCollaborati • ve and cross-functional mindsetOwnership -driven and proactive execution