Fullstack Developer

BilgeAdam Technologies GmbH; Fatih; On-site; TRY 350,000 - 650,000; Full time

Job summary

BilgeAdam Technologies GmbH is seeking a software engineer to design multi-agent workflows using LangGraph or similar orchestration frameworks. You will develop backend services in Python and/or Java, and build front-end interfaces with React, exposing agent behavior and traces.

Requirements: 4+ years producing production software in Python or Java; strong in one, fluent in the other; experience with Docker, Git, CI/CD, and cloud platforms; English communication is required.

Qualifications

• 4+ years building production software in Python and/or Java.
• Experience with agentic frameworks and orchestration tools.
• Understanding failure modes like hallucinations and prompt injections.

Responsibilities

• Design and build multi-agent workflows using LangGraph or similar orchestration frameworks.
• Develop production backend services in Python and/or Java with clean API design.
• Build front-end interfaces (React or similar) exposing agent behaviour, traces, and human intervention points.
• Implement retrieval pipelines: chunking, embeddings, vector stores, and hybrid search.
• Instrument everything with tracing, monitoring, and regression testing.
• Deploy and operate on cloud infrastructure with containers and CI/CD.
• Collaborate with architects and clients to translate requirements into working systems.

Skills

Python

Java

English communication

Tools

Docker

Git

CI/CD

Cloud platforms

Job description

• Design and build multi-agent and agentic workflows using LangGraph or comparable orchestration frameworks — state machines, tool use, memory, retries, and human approval gates.
  
• Develop production backend services in Python and/or Java, with clean API design, sound data modelling, and real test coverage.
  
• Build front-end interfaces (React or similar) that expose agent behaviour clearly — traces, intermediate steps, confidence, and points of human intervention.
  
• Implement retrieval pipelines: chunking, embeddings, vector stores, hybrid search, and evaluation of what actually improves answer quality.
  
• Instrument everything. Evaluation harnesses, tracing, cost and latency monitoring, regression testing of prompts and graphs.
  
• Deploy and operate on cloud infrastructure with containers and CI/CD.
  
• Work directly with architects and clients — translating requirements into working systems, and pushing back when the requirement is wrong.
  

Requirements

• 4+ years building production software in Python and/or Java. Strength in one and working fluency in the other is fine.
  
• Demonstrable experience with agentic frameworks — LangGraph, LangChain, CrewAI, AutoGen, the OpenAI or Anthropic SDKs, MCP — including systems that made it past the prototype stage.
  
• Understanding of the failure modes: hallucination, prompt injection, tool misuse, runaway cost, non-determinism — and the engineering patterns that contain them.
  
• Comfort with Docker, Git, CI/CD, and at least one major cloud provider.
  
• Clear communication in English, written and spoken.
  

Nice to have

• Financial services or other regulated-domain experience.
  
• Model evaluation and observability tooling (LangSmith, Langfuse, Weights & Biases, or equivalent).
  
• Kubernetes, infrastructure as code, or platform engineering background.