Sr AI/LLM Engineer and Python Backend Engineer
Frisco, Texas, United States of America
Contract
1 day ago
Key skills
AIMLLLMOpenAIRAGLangChainLangGraphQdrantMilvusETLELTData EngineeringReactFastAPIAzureBlob StoragePub/SubOAuthREST APIBudgeting
About this role
Title: Sr AI/LLM Engineer Location: Frisco & Irving, TX (Hybrid) Duration: 6 months (possibility of an extension)
and GC
Overall 8+ years experience with 5+ years in AI development. PFB the technology skills required.Core Language & ArchitecturePython 3.11+Advanced type hints (PEP 484), static typing disciplineAsync programming (asyncio, async/await, async generators)aiohttp / httpx (async HTTP clients)Pydantic v2 (BaseModel, validation, settings management)Structured logging & tracing patternsRedis (pub/sub, TTL, async clients)REST API design & integration patternsRetry/backoff strategies (Tenacity)Concurrency patterns (parallel tool calls, task orchestration)AI / LLM / Agent SystemsLangGraph (state machines, conditional edges, checkpointing)LangChain 0.3.x (LLMChain, StructuredTool, retrievers, prompt templates)ReAct-style agent architecturesTool-based agent design (40+ tool environments)Azure OpenAI / OpenAI APIs (GPT-4o, deployment mgmt, rate limits, token budgeting)Prompt engineering (few-shot, structured output, JSON mode)PydanticOutputParser / structured LLM responsesGuardrails / PII redaction patternsMemory abstractions for agentsLangfuse (trace instrumentation, evaluation, prompt management)LLM fallback chains & error recoveryRAG prompt grounding strategiesLLM fine-tuningNeural Network training & tuningTraditional ML models (random forest, k-means clustering, linear regression, etc.)MCP development and consumption Retrieval, Search & RAG EngineeringVector databases (Qdrant and/or Milvus)HNSW indexing parametersFiltering strategiesEmbedding pipelines (OpenAI ada-002 or equivalent)Batch embedding & re-indexing workflowsHybrid retrieval (BM25 + semantic)Score fusion strategiesCross-encoder reranking (BAAI/bge models)FastAPI-based inference servicesLangChain retriever abstractionsRAG evaluation metrics:FaithfulnessRelevanceNDCGMRRTrace-level RAG evaluation (Langfuse)Data Engineering & ETLPrefect 2.x / 3.xFlows, tasks, futuresDeployments (YAML)SchedulingETL/ELT designSchema evolutionQuery optimizationOAuth authenticationWarehouse/schema managementPostgreSQL 16/17psycopg 3.xConnection poolingSQLAlchemy 2.x (ORM + asyncio)Alembic migrationsAdvanced SQLMulti-table JOINsCTEsWindow functionsTimezone conversionPandas 2.x (complex multi-stage transformations)PyArrow / columnar formatsAzure Blob Storage (azure-storage-blob)Document ingestion/parsing:DoclingUnstructuredpython-docxpython-pptxDevOps & PlatformDockerLinux fundamentalsNice-to-HavesRay (distributed execution)Columnar performance tuningNetwork operations domain knowledgeNOC / alarm correlation familiarity API & Enterprise IntegrationsOAuth 2.0 (client credentials flow, token lifecycle)MSAL (browser + service principal flows)Microsoft Graph APISharePointOutlookPlannerOneDrivePaginationApp permissionsServiceNow REST APITable APIIncident/change mgmtBulk operationsSplunk SDKSaved searchesAsync queriesLog analysisAzure AD app registrationsIPAM / OTNA integrations (nice-to-have domain exposure)