Junior Software Engineer

Role: Junior Software Engineer (Python)Location: 4 days onsite and 1 remote. 14810 Grasslands Dr, Englewood CODescription:Follows company software development lifecycle to design, code, configure, test, debug, and document system and application programs. Assists in preparing technical design specifications based on functional requirements and analysis documents. Reviews functional requirements, analysis and design documents and provides feedback. Collaborates with other development staff to achieve quality and consistency. Participates in architecture, design and code reviews. . Develops and maintains operational and system level documentation. 1 - 5 years of experience.Python Backend DevelopmentPython 3.10+ (type hints, async/await, dataclasses, protocols)Web frameworks: FastAPI, Flask, or DjangoREST API and GraphQL designAsync programming with asyncio, aiohttpDependency injection, middleware patternsPydantic for data validation and serializationTesting: pytest, unittest, mocking, integration testsRAG (Retrieval-Augmented Generation)End-to-end RAG pipeline design and implementationDocument ingestion: chunking strategies (recursive, semantic, token-based)Embedding models: OpenAI, Cohere, Sentence Transformers, BGERetrieval strategies: dense retrieval, hybrid search (BM25 + vector), re-rankingContext window management and prompt engineeringProven usage of RAG in previous projectsVector DatabasesHands-on with at least 2: Pinecone, Weaviate, Milvus, Qdrant, ChromaDB, pgvectorIndexing algorithms: HNSW, IVF, PQ (product quantization)Metadata filtering, namespace managementHybrid storage patterns (vector + relational)LLM & AI FrameworksLangChain / LlamaIndex for orchestrationOpenAI API, Anthropic API, Azure OpenAI, AWS BedrockHugging Face Transformers and inference pipelinesFine-tuning concepts (LoRA, QLoRA) — awareness levelPrompt engineering and templatingFunction calling / tool use with LLMsGuardrails and output validationInfrastructure & Data EngineeringDocker, Docker Compose, Kubernetes basicsCI/CD pipelines (GitHub Actions, GitLab CI)Cloud platforms: AWS (S3, Lambda, SageMaker, Bedrock) or GCP/Azure equivalentsMessage queues: Celery, Redis, RabbitMQ, or KafkaDatabase: PostgreSQL, MongoDB, RedisObservability: logging, tracing (OpenTelemetry), LLM-specific monitoring (LangSmith, Weights & Biases)