22 hours ago
Noida, IndiaSenior / Staff+
Responsibilities
- Design multi-agent systems using orchestration frameworks such as LangGraph, AutoGen, CrewAI, and Google ADK.
- Build LLM services with prompt engineering, tool and function calling, planning, memory, reflection, guardrails, fallback patterns, and RAG.
- Integrate and evaluate commercial API-based and open-source or self-hosted LLMs while balancing cost, latency, accuracy, privacy, and complexity.
- Build and manage vector database-backed RAG pipelines, embeddings, hybrid search, re-ranking, and index lifecycles.
- Model and query property graphs and RDF/ontologies for agent context, semantic reasoning, and structured retrieval.
- Create evaluation harnesses using automated scoring, human review, A/B testing, and golden datasets.
- Develop ML pipelines for feature engineering, training, evaluation, serving, fine-tuning, packaging, versioning, and monitoring.
- Develop testable Python and PySpark services and REST, FastAPI, Flask, and gRPC APIs.
- Monitor model drift, data quality, performance, latency, and token costs in production.
- Contribute to CI/CD, code reviews, architecture discussions, documentation, runbooks, and mentoring.
Requirements
- 6–15 years of software development experience.
- 5+ years of hands-on ML engineering and LLM development experience in production.
- Bachelor’s or Master’s degree in Computer Science, Software Engineering, AI/ML, or equivalent experience.
- Production experience with Agentic AI, vector database-backed RAG, and knowledge graph integrations.
- Expert Java and Python skills; PySpark is desirable.
- Experience with Spark, SQL, Pandas or Polars, structured streaming, Delta Lake or Iceberg, and Kafka or Pulsar.
- Knowledge of LLM fine-tuning and optimization, including LoRA, QLoRA, RLHF, ONNX, TensorRT, quantization, and efficient inference.
- Experience with Docker, Kubernetes, AWS, Azure, GCP, Databricks or EMR, and MLOps tools such as MLflow or Weights & Biases.
- Knowledge of LLM observability, structured logging, token-cost tracking, alerting, responsible AI, and model safety.
- Working knowledge of TOGAF or an equivalent enterprise architecture framework and technical documentation standards.
- Academic credentials must come from recognized and accredited institutions and are subject to verification.
Benefits
- Opportunity to work on intelligent automation and decision-support systems for telecom-scale managed services.
- Collaborative environment with platform engineers, data scientists, and product owners.
- Equal opportunity workplace that encourages applicants from diverse backgrounds.
- Location: Noida, India.
Tech Stack
Apache KafkaApache SparkAWSAzureDatabricksDockerFastAPIFlaskGitHub ActionsGoogle Cloud PlatformgRPCJavaJenkinsKubernetesMLflowPandasPythonPyTorchscikit-learnSQL
Categories
About Ericsson
Ericsson is a publicly traded telecommunications vendor that builds mobile network infrastructure (RAN, core, OSS/BSS), cloud platforms, and managed services for communications providers and enterprises. Founded in 1876 and headquartered in Kista, Stockholm, it supplies 5G systems to operators worldwide and owns Vonage, expanding network APIs and enterprise communications offerings.