Job Requirements AI/Python/Java Developer (4 Years Experience)
Core AI / ML Experience
4+ years of hands-on experience building and deploying production AI/GenAI applications
Experience designing and orchestrating multi-agent LLM workflows (e.g., Google ADK, LangChain, or equivalent agentic frameworks)
Practical experience with Retrieval-Augmented Generation (RAG) chunking strategies, vector similarity search, semantic regrouping
Familiarity with prompt engineering, instruction tuning, and evaluating LLM output quality (confidence calibration, citation accuracy)
Experience integrating LLMs via gateway proxies (e.g., LiteLLM, Azure OpenAI, or enterprise LLM routing layers)
Understanding of LLM output parsing, structured JSON extraction, and handling model response variability
Experience with feedback loop design capturing human corrections and injecting rules back into inference pipelines
Python
4+ years Python development; proficient in FastAPI or equivalent async web frameworks
Strong working knowledge of SQLAlchemy (sync and async), Pydantic v2, and asyncpg for PostgreSQL
Comfortable with Python dependency management using Poetry or uv; experience with private PyPI registries (e.g., JFrog Artifactory)
Experience writing and maintaining YAML-driven workflow configurations for agent orchestration pipelines
Familiarity with pytest, integration testing patterns, and mocking LLM responses in test suites
Proficient with data processing libraries: pandas, json-logic, rapidfuzz
Java
3+ years Java/Spring Boot development for microservices
Experience with Spring JPA/Hibernate against Oracle or relational databases
Familiarity with ISC or event-bus patterns for JVM-local async messaging
Exposure to SOAP/XML integrations (JAXB marshalling, NCPDP or HL7 a plus)
Experience with feature flag patterns, service layer orchestration, and finally-block-driven reliability patterns
Google Cloud Platform / GKE / Cloud Infrastructure
Experience deploying containerized services to Google Kubernetes Engine (GKE)
Familiarity with Google Cloud Storage (GCS) for artifact and data management
Hands-on with Google Gemini models (Flash or Pro variants) via Vertex AI or direct API
Understanding of Google Cloud Platform IAM, service accounts, and quota management for LLM API access
Experience with Kubernetes resource tuning replica sets, pod autoscaling, resource requests/limits
Familiarity with CI/CD pipelines targeting GKE (e.g., Harness, GitHub Actions, or equivalent)
Experience with Google Cloud Platform monitoring, logging (Cloud Logging), and tracing for distributed Python/Java services
Databases
Experience with dual-database architectures: Oracle (Java/JPA) and PostgreSQL (Python/SQLAlchemy)
Comfortable writing and optimizing SQL for operational and analytical queries
Familiarity with connection pool tuning (pool size, overflow, pre-ping, LIFO strategies)
General Engineering
Experience building systems with strict human-in-the-loop requirements output review, correction capture, and audit trails
Comfortable working across a polyglot microservices architecture (Java on-prem + Python on GKE)
Strong understanding of REST API design, async event-driven patterns, and retry/backoff strategies
Experience with healthcare data standards (NCPDP, HL7 FHIR, or EHR integration) is a strong plus
Familiarity with secure coding practices: masked PII before LLM calls, HMAC authentication, SSL/TLS cert management
Never miss an opportunity! Create an alert based on the job you applied for.
